HeightNet: Monocular Object Height Estimation

Abstract

Monocular depth estimation is a traditional computer vision task that predicts the distance of each pixel relative to the camera from one 2D image. Relative height information about objects lying on a ground plane can be calculated through several processing steps from the depth image. In this paper, we propose a height estimation method for directly predicting the height of objects from a 2D image. The proposed method utilizes an encoder-decoder network for pixel-wise dense prediction based on height consistency. We used the CARLA simulator to generate 40,000 training datasets from different positions in five areas within the simulator. The experimental results show that the object’s height map can be estimated regardless of the camera’s location.

Edge-Enhanced Dual-Stream Perception Network for Monocular Depth Estimation

“…In recent years, numerous researchers have introduced various monocular image depth estimation models based on the encoder-decoder architecture, as shown in Figure 1 [14,15]. This architecture is divided into two parts: the encoder, which extracts depth features from images, and the decoder, which predicts depth information.…”